CTS-Net: A Segmentation Network for Glaucoma Optical Coherence Tomography Retinal Layer Images
Optical Coherence Tomography (OCT) technology is essential to obtain glaucoma diagnostic data non-invasively and rapidly. Early diagnosis of glaucoma can be achieved by analyzing the thickness and shape of retinal layers. Accurate retinal layer segmentation assists ophthalmologists in improving the...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-02-01
|
Series: | Bioengineering |
Subjects: | |
Online Access: | https://www.mdpi.com/2306-5354/10/2/230 |
_version_ | 1797622260237860864 |
---|---|
author | Songfeng Xue Haoran Wang Xinyu Guo Mingyang Sun Kaiwen Song Yanbin Shao Hongwei Zhang Tianyu Zhang |
author_facet | Songfeng Xue Haoran Wang Xinyu Guo Mingyang Sun Kaiwen Song Yanbin Shao Hongwei Zhang Tianyu Zhang |
author_sort | Songfeng Xue |
collection | DOAJ |
description | Optical Coherence Tomography (OCT) technology is essential to obtain glaucoma diagnostic data non-invasively and rapidly. Early diagnosis of glaucoma can be achieved by analyzing the thickness and shape of retinal layers. Accurate retinal layer segmentation assists ophthalmologists in improving the efficiency of disease diagnosis. Deep learning technology is one of the most effective methods for processing OCT retinal layer images, which can segment different retinal layers and effectively obtain the topological structure of the boundary. This paper proposes a neural network method for retinal layer segmentation based on the CSWin Transformer (CTS-Net), which can achieve pixel-level segmentation and obtain smooth boundaries. A Dice loss function based on boundary areas (BADice Loss) is proposed to make CTS-Net learn more features of edge regions and improve the accuracy of boundary segmentation. We applied the model to the publicly available dataset of glaucoma retina, and the test results showed that mean absolute distance (MAD), root mean square error (RMSE), and dice-similarity coefficient (DSC) metrics were 1.79 pixels, 2.15 pixels, and 92.79%, respectively, which are better than those of the compared model. In the cross-validation experiment, the ranges of MAD, RMSE, and DSC are 0.05 pixels, 0.03 pixels, and 0.33%, respectively, with a slight difference, which further verifies the generalization ability of CTS-Net. |
first_indexed | 2024-03-11T09:08:36Z |
format | Article |
id | doaj.art-1374d5016a4e4e90ae33947e5a6c0c54 |
institution | Directory Open Access Journal |
issn | 2306-5354 |
language | English |
last_indexed | 2024-03-11T09:08:36Z |
publishDate | 2023-02-01 |
publisher | MDPI AG |
record_format | Article |
series | Bioengineering |
spelling | doaj.art-1374d5016a4e4e90ae33947e5a6c0c542023-11-16T19:11:29ZengMDPI AGBioengineering2306-53542023-02-0110223010.3390/bioengineering10020230CTS-Net: A Segmentation Network for Glaucoma Optical Coherence Tomography Retinal Layer ImagesSongfeng Xue0Haoran Wang1Xinyu Guo2Mingyang Sun3Kaiwen Song4Yanbin Shao5Hongwei Zhang6Tianyu Zhang7Key Laboratory of Geophysical Exploration Equipment, Ministry of Education, College of Instrumentation and Electrical Engineering, Jilin University, Changchun 130000, ChinaKey Laboratory of Geophysical Exploration Equipment, Ministry of Education, College of Instrumentation and Electrical Engineering, Jilin University, Changchun 130000, ChinaKey Laboratory of Geophysical Exploration Equipment, Ministry of Education, College of Instrumentation and Electrical Engineering, Jilin University, Changchun 130000, ChinaKey Laboratory of Geophysical Exploration Equipment, Ministry of Education, College of Instrumentation and Electrical Engineering, Jilin University, Changchun 130000, ChinaKey Laboratory of Geophysical Exploration Equipment, Ministry of Education, College of Instrumentation and Electrical Engineering, Jilin University, Changchun 130000, ChinaKey Laboratory of Geophysical Exploration Equipment, Ministry of Education, College of Instrumentation and Electrical Engineering, Jilin University, Changchun 130000, ChinaKey Laboratory of Geophysical Exploration Equipment, Ministry of Education, College of Instrumentation and Electrical Engineering, Jilin University, Changchun 130000, ChinaKey Laboratory of Geophysical Exploration Equipment, Ministry of Education, College of Instrumentation and Electrical Engineering, Jilin University, Changchun 130000, ChinaOptical Coherence Tomography (OCT) technology is essential to obtain glaucoma diagnostic data non-invasively and rapidly. Early diagnosis of glaucoma can be achieved by analyzing the thickness and shape of retinal layers. Accurate retinal layer segmentation assists ophthalmologists in improving the efficiency of disease diagnosis. Deep learning technology is one of the most effective methods for processing OCT retinal layer images, which can segment different retinal layers and effectively obtain the topological structure of the boundary. This paper proposes a neural network method for retinal layer segmentation based on the CSWin Transformer (CTS-Net), which can achieve pixel-level segmentation and obtain smooth boundaries. A Dice loss function based on boundary areas (BADice Loss) is proposed to make CTS-Net learn more features of edge regions and improve the accuracy of boundary segmentation. We applied the model to the publicly available dataset of glaucoma retina, and the test results showed that mean absolute distance (MAD), root mean square error (RMSE), and dice-similarity coefficient (DSC) metrics were 1.79 pixels, 2.15 pixels, and 92.79%, respectively, which are better than those of the compared model. In the cross-validation experiment, the ranges of MAD, RMSE, and DSC are 0.05 pixels, 0.03 pixels, and 0.33%, respectively, with a slight difference, which further verifies the generalization ability of CTS-Net.https://www.mdpi.com/2306-5354/10/2/230glaucomadeep learningloss functionretinal layer segmentationoptical coherence tomography |
spellingShingle | Songfeng Xue Haoran Wang Xinyu Guo Mingyang Sun Kaiwen Song Yanbin Shao Hongwei Zhang Tianyu Zhang CTS-Net: A Segmentation Network for Glaucoma Optical Coherence Tomography Retinal Layer Images Bioengineering glaucoma deep learning loss function retinal layer segmentation optical coherence tomography |
title | CTS-Net: A Segmentation Network for Glaucoma Optical Coherence Tomography Retinal Layer Images |
title_full | CTS-Net: A Segmentation Network for Glaucoma Optical Coherence Tomography Retinal Layer Images |
title_fullStr | CTS-Net: A Segmentation Network for Glaucoma Optical Coherence Tomography Retinal Layer Images |
title_full_unstemmed | CTS-Net: A Segmentation Network for Glaucoma Optical Coherence Tomography Retinal Layer Images |
title_short | CTS-Net: A Segmentation Network for Glaucoma Optical Coherence Tomography Retinal Layer Images |
title_sort | cts net a segmentation network for glaucoma optical coherence tomography retinal layer images |
topic | glaucoma deep learning loss function retinal layer segmentation optical coherence tomography |
url | https://www.mdpi.com/2306-5354/10/2/230 |
work_keys_str_mv | AT songfengxue ctsnetasegmentationnetworkforglaucomaopticalcoherencetomographyretinallayerimages AT haoranwang ctsnetasegmentationnetworkforglaucomaopticalcoherencetomographyretinallayerimages AT xinyuguo ctsnetasegmentationnetworkforglaucomaopticalcoherencetomographyretinallayerimages AT mingyangsun ctsnetasegmentationnetworkforglaucomaopticalcoherencetomographyretinallayerimages AT kaiwensong ctsnetasegmentationnetworkforglaucomaopticalcoherencetomographyretinallayerimages AT yanbinshao ctsnetasegmentationnetworkforglaucomaopticalcoherencetomographyretinallayerimages AT hongweizhang ctsnetasegmentationnetworkforglaucomaopticalcoherencetomographyretinallayerimages AT tianyuzhang ctsnetasegmentationnetworkforglaucomaopticalcoherencetomographyretinallayerimages |